AnalyzeDoc Jobs

Create and manage AnalyzeDoc document analysis jobs

List AnalyzeDoc job history

GET

https://gw.ldxhub.io

/analyzedoc/jobs

Returns a list of jobs for the authenticated user, ordered by creation date descending. Use GET /analyzedoc/jobs/{job_id} to retrieve full details for a specific job.

List AnalyzeDoc job history › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

List AnalyzeDoc job history › Responses

A list of jobs

AnalyzeDocJobSummary[]

Create an AnalyzeDoc job

POST

https://gw.ldxhub.io

/analyzedoc/jobs

Enqueues an asynchronous document analysis job. Upload your PDF or image file via POST /files first, then submit the file_id here. The vision AI model reads the document and returns structured JSON following your example_output. Returns 202 Accepted immediately with a job_id. Poll GET /analyzedoc/jobs/{job_id} to check completion. When completed, download the extracted JSON via GET /files/{output_file_id}/content.

Supported input formats: PDF, JPEG, PNG. The input format is automatically detected from the uploaded file. Format support varies by model — the request is rejected with 400 if the selected model does not support the detected input format.

Create an AnalyzeDoc job › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Create an AnalyzeDoc job › Request Body

AnalyzeDocCreateJobRequest

model

string · required

Model ID obtained from GET /analyzedoc/models, including the resolution variant suffix (e.g. '@high').

system_prompt

string · required

Instruction describing what structured data to extract from the document and how

example_output

object · required

A JSON object showing the desired output structure with example values. Key order matters: it guides the order in which fields are generated (a hint, not a guarantee), so place discriminator fields such as 'type' first. Keys set to null in the example become optional in the output.

file_id

string · required

File ID of the input document to analyze, obtained from POST /files. Supported input formats: PDF, JPEG, PNG. The input format is automatically detected from the uploaded file. Format support varies by model — check 'supported_conversions' in GET /analyzedoc/models.

output_format

string · enum · required

Output format

Enum values:

json

Create an AnalyzeDoc job › Responses

Job accepted

Response returned immediately after job submission

JobCreateResponse

job_id

string

Unique job identifier. Use this to poll for results.

model

string

status

string · enum

Enum values:

queued

progress

number · float

created_at

string · date-time

updated_at

string · date-time

expires_at

string · date-time

POST/analyzedoc/jobs

curl https://gw.ldxhub.io/analyzedoc/jobs \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <token>' \
  --data '{
  "model": "openai/gpt-5.5@high",
  "system_prompt": "Extract the invoice number, vendor name, and total amount from the document.",
  "example_output": {
    "invoice_number": "INV-2026-001",
    "vendor": "Acme Corp",
    "total_amount": 125000
  },
  "file_id": "ako5rgx309ehwlbqprs8s2xxnsp0y85q",
  "output_format": "json"
}'

Example Request Body

{
  "model": "openai/gpt-5.5@high",
  "system_prompt": "Extract the invoice number, vendor name, and total amount from the document.",
  "example_output": {
    "invoice_number": "INV-2026-001",
    "vendor": "Acme Corp",
    "total_amount": 125000
  },
  "file_id": "ako5rgx309ehwlbqprs8s2xxnsp0y85q",
  "output_format": "json"
}

json

application/json

Example Responses

{
  "job_id": "am60z92bmdwphs95dxclndk3erh3x8jy",
  "model": "openai/gpt-5.5@high",
  "status": "queued",
  "progress": 0,
  "created_at": "2026-07-02T09:15:11Z",
  "updated_at": "2026-07-02T09:15:11Z",
  "expires_at": "2026-07-03T09:15:11Z"
}

json

application/json

Get AnalyzeDoc job status and results

GET

https://gw.ldxhub.io

/analyzedoc/jobs/{job_id}

Returns the current status of an AnalyzeDoc job. Poll this endpoint until status is completed or failed. Recommended polling interval: 1-5 seconds. When status is completed, use output_file_id to download the extracted JSON via GET /files/{output_file_id}/content. Results are retained for a limited period after completion (expires_at).

Get AnalyzeDoc job status and results › path Parameters

job_id

string · required

The unique identifier of the job

Get AnalyzeDoc job status and results › Headers

Authorization

string · required

The Authorization header is used to authenticate with the API using your API key. Value is of the format Bearer YOUR_KEY_HERE.

Get AnalyzeDoc job status and results › Responses

Job details

Full job details. Returned by GET /analyzedoc/jobs/{job_id}.

AnalyzeDocJobDetail

job_id

string

file_id

string

Input file ID

model

string

status

string · enum

Enum values:

queued

processing

completed

failed

progress

number · float

output_file_id

string

File ID of the extracted JSON output. Present only when status is completed. Download via GET /files/{output_file_id}/content.

JobError

Job-level error. Present only when job status is failed.

created_at

string · date-time

updated_at

string · date-time

completed_at

string · date-time

expires_at

string · date-time

Usage

AnalyzeDoc Models RefineLoop Models